Training in progress, step 1000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "datificate/gpt2-small-spanish",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.0",
+  "use_cache": true,
+  "vocab_size": 50385
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94bd9440e2cb45d55069f2489713f6f28f1d2b76f570580b35b2379cb92a05a6
+size 510787305

runs/Aug04_08-38-19_11308a68b9eb/1659603031.7368438/events.out.tfevents.1659603031.11308a68b9eb.55.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982424e918043773796e944bfb95c1f5f1d1462d8c0bccfed35bb39c6b3cef1c
+size 5421

runs/Aug04_08-38-19_11308a68b9eb/events.out.tfevents.1659602527.11308a68b9eb.55.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0232ae170f52d6dbfceea2cec7942dba4d31485ba6951f78101734845e71fd2c
+size 4476

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7fa38ece32c4d56d576b41c278fd37888e0a74998b20df997a04ac322a90ef
+size 3311